TTS声音合成：paddlespeech、sherpa-onnx、coqui-ai

本文介绍: 中文下载链接：https://github.com/coqui–ai/TTS/release s/download/v0.6.1_models/tts_models–zh-CN–b a k e r–t a cot r on2-DDC-GST.zip。参考：https://github.com/k2-fsa/sh erp a–onnx/blob/master/python–api–examples/off line–tts.py。参考：https://modelscope.cn/models?coqui–ai/TTS 语音合成。

参考：
https://ai studio.baidu.co m/ai studio/project de tail/5237474
https://www.ji ans hu.co m/p/a7522ca6de c4
https://git hub.co m/Pa ddl ePa ddl e/Pa ddl eSpeech/blob/devel op/demo s/text_t o_speech/README_cn.md

1）过程中需要下载的TTS 声学相关模型（网络不好的话下面链接可以离线下载）：

PaddleSpeech支持的声学模型：
 ['speedyspeech_csmsc-zh', 'fastspeech2_csmsc-zh', 'fastspeech2_canton-canton', 'fastspeech2_ljspeech-en', 'fastspeech2_aishell3-zh', 'fastspeech2_vctk-en', 'fastspeech2_cnndecoder_csmsc-zh', 'fastspeech2_mix-mix', 'fastspeech2_male-zh', 'fastspeech2_male-en', 'fastspeech2_male-mix', 'tacotron2_csmsc-zh', 'tacotron2_ljspeech-en', 'pwgan_csmsc-zh', 'pwgan_ljspeech-en', 'pwgan_aishell3-zh', 'pwgan_vctk-en', 'pwgan_male-zh', 'mb_melgan_csmsc-zh', 'style_melga